mistral_instruct_generation

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6932

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
2.6515	0.0024	20	2.7542
2.6869	0.0048	40	2.7300
2.6922	0.0073	60	2.7081
2.7005	0.0097	80	2.6988
2.7012	0.0121	100	2.6932

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1